Min Lin

Min Linhttps://linmin.me/Recent content on Min LinHugo -- gohugo.ioen-usWed, 30 Oct 2024 00:00:00 +0000Richard Sutton talk about continual learning.https://linmin.me/posts/richard_sutton_talk_about_continual_learning/Wed, 30 Oct 2024 00:00:00 +0000https://linmin.me/posts/richard_sutton_talk_about_continual_learning/Philosophical bits that I collected over the years for building AI.https://linmin.me/posts/philosophical_bits/Sun, 03 Mar 2024 00:00:00 +0000https://linmin.me/posts/philosophical_bits/ML Systemshttps://linmin.me/posts/mlsys/Fri, 23 Feb 2024 00:00:00 +0000https://linmin.me/posts/mlsys/AI for Sciencehttps://linmin.me/posts/ai_for_science/Thu, 22 Feb 2024 00:00:00 +0000https://linmin.me/posts/ai_for_science/<link>https://linmin.me/about/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://linmin.me/about/</guid><description/></item><item><title/><link>https://linmin.me/publications/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://linmin.me/publications/</guid><description>Google Scholar Selected Publication & Preprints Machine Learning Understanding R1-Zero-Like Training: A Critical Perspective Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, Min Lin. COLM 2025 Locality Sensitive Sparse Encoding for Learning World Models Online Zichen Liu, Chao Du, Wee Sun Lee, Min Lin. ICLR 2024 Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows Chao Du, Tianbo Li, Tianyu Pang, Shuicheng Yan, Min Lin.</description></item><item><title/><link>https://linmin.me/research/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://linmin.me/research/</guid><description>This page is updated time to time Central research question What is the universal algorithm, once deployed into interation with the world, will learn by itself and finally induce General Intelligence? Apparently human brain contains such an algorithm. Let’s call it General Learner to distinguish from General Intelligence. It seems some deep learning system is close to achieving General Intelligence, yet none of them are General Learners. A deep learning model has clear phases in its life cycle, pretraining, finetuning, inference etc.</description></item><item><title/><link>https://linmin.me/software/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://linmin.me/software/</guid><description>Software autofd Provides automatic differentiation for functionals (variational calculus). We use it for density functional theory. jax-xc Exchange correlation functionals translated from libxc to JAX. Towards a deep learning native library for density functional theory (DFT). envpool High performance, parallel RL environment executor baked with C++. wrap_dll Handy tool to inject code into windows DLL. I used it to intercept function calls into the AudioSes.dll, to capture all audio streams played by any application.</description></item></channel></rss>